{"id":"https://openalex.org/W3136644942","doi":"https://doi.org/10.1109/lsp.2021.3065598","title":"Multimodal Embeddings From Language Models for Emotion Recognition in the Wild","display_name":"Multimodal Embeddings From Language Models for Emotion Recognition in the Wild","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3136644942","doi":"https://doi.org/10.1109/lsp.2021.3065598","mag":"3136644942"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2021.3065598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3065598","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003744098","display_name":"Shao-Yen Tseng","orcid":"https://orcid.org/0000-0003-1795-8330"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shao-Yen Tseng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1795-8330","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021678540","display_name":"Panayiotis Georgiou","orcid":"https://orcid.org/0000-0002-0790-7161"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panayiotis Georgiou","raw_affiliation_strings":["Siri Understanding, Apple Inc., Culver City, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0790-7161","affiliations":[{"raw_affiliation_string":"Siri Understanding, Apple Inc., Culver City, CA, USA","institution_ids":["https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8449,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90260762,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"608","last_page":"612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8344410061836243},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.7252223491668701},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7029227018356323},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5793060660362244},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5648595094680786},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.539749264717102},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5270716547966003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5035917162895203},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4498264193534851},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.445597380399704},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.42978036403656006},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.40727493166923523},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18884143233299255},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.11011525988578796},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09139105677604675}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8344410061836243},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7252223491668701},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7029227018356323},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5793060660362244},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5648595094680786},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.539749264717102},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5270716547966003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5035917162895203},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4498264193534851},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.445597380399704},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.42978036403656006},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40727493166923523},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18884143233299255},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.11011525988578796},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09139105677604675},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2021.3065598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3065598","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1938755728","https://openalex.org/W1965069145","https://openalex.org/W1988085234","https://openalex.org/W2014399678","https://openalex.org/W2095176743","https://openalex.org/W2143350951","https://openalex.org/W2146334809","https://openalex.org/W2163922914","https://openalex.org/W2250539671","https://openalex.org/W2259472270","https://openalex.org/W2342475039","https://openalex.org/W2407023693","https://openalex.org/W2565875961","https://openalex.org/W2567070169","https://openalex.org/W2584561145","https://openalex.org/W2610961739","https://openalex.org/W2611669587","https://openalex.org/W2648194195","https://openalex.org/W2752172973","https://openalex.org/W2787560479","https://openalex.org/W2805122419","https://openalex.org/W2808359495","https://openalex.org/W2809734421","https://openalex.org/W2810643877","https://openalex.org/W2883409523","https://openalex.org/W2886193235","https://openalex.org/W2890560993","https://openalex.org/W2895433965","https://openalex.org/W2895486067","https://openalex.org/W2897182555","https://openalex.org/W2906626778","https://openalex.org/W2937584914","https://openalex.org/W2946218857","https://openalex.org/W2951559648","https://openalex.org/W2951714314","https://openalex.org/W2953104586","https://openalex.org/W2962718314","https://openalex.org/W2962739339","https://openalex.org/W2962770129","https://openalex.org/W2962883166","https://openalex.org/W2962885765","https://openalex.org/W2963341956","https://openalex.org/W2963685106","https://openalex.org/W2963800675","https://openalex.org/W2963970792","https://openalex.org/W2969035964","https://openalex.org/W2971393230","https://openalex.org/W2973037561","https://openalex.org/W3015906487","https://openalex.org/W4294491235","https://openalex.org/W6632248436","https://openalex.org/W6640598943","https://openalex.org/W6714171909","https://openalex.org/W6731370813","https://openalex.org/W6743384090","https://openalex.org/W6751883949","https://openalex.org/W6752074422","https://openalex.org/W6752724743","https://openalex.org/W6753277404","https://openalex.org/W6754723338","https://openalex.org/W6766533624"],"related_works":["https://openalex.org/W2375682379","https://openalex.org/W226586525","https://openalex.org/W1998541766","https://openalex.org/W2064542902","https://openalex.org/W2962716343","https://openalex.org/W2262900283","https://openalex.org/W178568469","https://openalex.org/W2765804957","https://openalex.org/W43702919","https://openalex.org/W2060410964"],"abstract_inverted_index":{"Word":[0],"embeddings":[1,47,80,101],"such":[2],"as":[3],"ELMo":[4],"and":[5,74,91],"BERT":[6],"have":[7],"been":[8],"shown":[9],"to":[10,55,102],"model":[11,63,84],"word":[12,89],"usage":[13],"in":[14,27],"language":[15,24,34,58,62,68],"with":[16],"greater":[17],"efficacy":[18],"through":[19,48],"contextualized":[20,45],"learning":[21],"on":[22,66],"large-scale":[23],"corpora,":[25],"resulting":[26],"significant":[28],"performance":[29],"improvement":[30],"across":[31],"many":[32],"natural":[33],"processing":[35],"tasks.":[36],"In":[37],"this":[38,83],"work":[39],"we":[40],"integrate":[41,85],"acoustic":[42],"information":[43,96],"into":[44,88],"lexical":[46],"the":[49,56,103],"addition":[50],"of":[51,105],"a":[52],"parallel":[53],"stream":[54],"bidirectional":[57],"model.":[59],"This":[60],"multimodal":[61,100],"is":[64],"trained":[65],"spoken":[67],"data":[69],"that":[70,79],"includes":[71],"both":[72],"text":[73],"audio":[75],"modalities.":[76],"We":[77],"show":[78],"extracted":[81],"from":[82],"paralinguistic":[86],"cues":[87],"meanings":[90],"can":[92],"provide":[93],"vital":[94],"affective":[95],"by":[97],"applying":[98],"these":[99],"task":[104],"speaker":[106],"emotion":[107],"recognition.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}